Prediction of Forging Ingots Defects Using Neural Networks

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F61989100%3A27230%2F11%3A86080579" target="_blank" >RIV/61989100:27230/11:86080579 - isvavai.cz</a>
Alternative codes found
RIV/61989100:27360/11:86080579 RIV/61989100:27240/11:86080579
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Prediction of Forging Ingots Defects Using Neural Networks
Original language description
At some types of ingots technological deviations exhibit by defects, which occur as late as in the process of forging. Prediction of such defects would enable a fast intervention and thus reducing costs for the reparation. Statistically was proven, thatthe defects are not caused by exceeding of any measured parameter in the production. However, they are caused by an unsuitable combination of more parameters. In such case artificial intelligence elements can be successfully applied. A multilayer artificial neural network was used for the prediction of defective ingots. Results, which were reached at prediction with neural network, are very interesting. In some cases even 100% accordance occurred.
Czech name
—
Czech description
—

Project
<a href="/en/project/FR-TI3%2F818" target="_blank" >FR-TI3/818: *EXTERNAL FIXATION</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Publication year
2011
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Recent Researches in Engineering and Automatic Control
ISBN
978-1-61804-057-2
ISSN
—
e-ISSN
—
Number of pages
4
Pages from-to
38-41
Publisher name
WSEAS Press
Place of publication
Neuvedeno
Event location
Puerto De La Cruz, Tenerife
Event date
Dec 10, 2011
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)